UNDER CONSTRUCTION. CS 622 Computer Vision (Spring 2003)

Quick Links:
Topics
Tasks
Grades So Far
Evaluation
Texts
Announcements
Resources
Midsemester Course Eval		 Instructors: Sharat Chandran and Neelima Shrikhande. Use neelima AT surya to send email.
Office: F19 CSE Building
Office Hours: To Be Announced.
Office Phone: 7724 and 7726
Lecture hours: Tuesday 2:00 PM, Thursday 5:00 PM
Lab: There is no formal lab hour.
Venue for the course: Seminar Room
Teaching Assistant: None.
  • Recent Announcements (Last Modified -- make sure you have the timezone right! )
    1. End sem exam is over! Thank you for the course!
    2. Grades have been updated (in a hurry, so I might have made some mistakes). I will set up a time for you to look at your final exam answer books and to discuss your grades (if you have any questions). Do not send me email (unless there is an emergency).
  • Course Overview: In this course we present some techniques for understanding images. We shall, however, explore at least two topics in more depth than it warrants a first level course.
  • Texts: Note the description in the text section.
  • Course Prerequisites: Student are expected to have basic programming skills (programming with loops, pointers, structures, recursion), discrete mathematics (probability), and matrix methods.
  • What will be covered next:
    1. Tuesday topics: Official Holiday
    2. Thursday topics: Last two papers
  • Topics Covered.
    1. 12/31. Introduction to Computer Vision. Slides. Lots of pictures/demos that I showed do not appear here.
    2. 1/6. Calculus of variations. Slides. Method of Lagrange multiplier, variational calculus intro.
    3. 1/7. Overview of a typical vision application. Slides. Glimpse of Codons.
    4. 1/8. Extra lecture from Prof. Larry Davis. How to detect moving objects under occlusion.
    5. 1/14. Edges Slides. Canny detector.
    6. 1/16. Segmentation. Boundary following. Slides.
    7. 1/21. Corners. Slides. A bit of ev/evalue stuff.
    8. 1/23. Connecting the dots, and the Hough transforms. Slides.
    9. 1/28. The Hough transform continued.
    10. 1/30. snakes. Slides.
    11. 2/04. Segmentation, Surface representation. Slides.
    12. 2/06. Surface representation. Slides. You might have to disable proxies while opening this presentation. (Mysteries of Microsoft!)
    13. 2/11. Matching. Slides.
    14. 2/13. Morphology Slides.
    15. 2/19. Exam.
    16. 2/20. Discussion on exam.
    17. 2/25. Veggie vision. Slides. Notes from Stockman book.
    18. 2/27. Texture Slides.
    19. 3/4. Color. Slides.
    20. 3/6. Content Based Image Retrieval using graphs Slides.
    21. 3/11. No class.
    22. 3/13. No class.
    23. 3/18. Holi Holiday.
    24. 3/20. Ragini Verma lecture. Relevant paper for evaluation purposes.
      Do NOT read exhaustively, just the main ideas. Specifically read the introduction and conclusion. By the way, use gv, not acroread.
    25. 3/25. Ramesh Visvanathan lecture on Real Time Vision. Relevant paper for evaluation purposes. (to be placed)
      Do NOT read exhaustively, just the main ideas.
    26. 3/27. Description of final assignment. Abbreviated class. Relevant description
      Relevant papers and list of papers.
    27. 4/1. Calibration Updates. Essential matrix. Slides.
    28. 4/3. Stereo Vision. Slides.
    29. 4/8. Presentation 1 and 2 (schneiderman+birchfield). Done!
    30. 4/10. Presentation 3 and 4 (poggio+wang) Done!
    31. 4/17. Presentation 5 and 6 (blake+ferris)
    32. 5/1. 9:30 AM Final Exam
  • Topics to be covered.
    Lecture 1Lecture 2
    Week 1 December 30Intro, Ch 1 (Websites, journals) Ch 2 (Optics, camera model, intensity and range images)
    Week 2 January 6Ch 3 (Noise, filtering,Gaussians) Overview of contour based object recognition
    Week 3 January 13Ch 4 (Image features, edges,surfaces, corner detection)Segmentation continued
    Week 4 January 20Ch 5 (Edge linking, curve fitting, least squares)Hough transforms
    Week 5 January 27Ch 6 (Camera calibration) continued
    Week 6 February 3Ch 10 (Model based recognition, interpretation trees, graphs)Geometric constraints(distances, angles between lines and surfaces)
    Week 7 February 10Codons and parts from contoursMidterm
    Week 8 February 17Curve and surface propertiescontinued
    Week 9 February 24Binary image analysisMorphology continued
    Week 10 March 3Ch 11, Rotations and translations
  • Resources, Demos, samples. I'll list some neat stuff that I come across on the Internet (typically Java applets). If you find something, please let me know so that I can list it here and give you brownie points!.
    1. Lena Off topic
    2. Veggie Vision On topic : your assignment.
  • Tasks. Assignments are not optional. You MUST submit every assignment (even if you are an audit student).
    1. Programming assignment 1 appears here. Consider usingx2 the small Java Vision Toolkit to read in your images. Look at the information in the Java image toolkit. Download the toolkit. Upload instructions will come in later.
    2. Written assignment 1 appears here.
  • Notes on evaluation.
    1. Grading (these numbers are approximate, the final numbers will be tweaked to give YOU the MAXIMUM possible grade).
      • One or two non-programming assignment (Total: 10%)
      • One midterm exam (About 25%)
      • Final exam: (About 25%)
      • One or two programming assignments (Total: 40%)
      • Class participation. (Grade breaker: Max of 5%)
    2. Collaboration: By default, you may discuss general ideas behind assignments with friends. However, you are expected to implement your own solutions. Please do not plagiarize from the Internet or other sources. By reading these lines, you agree to these terms :-)
    3. Attending the class is optional.
    4. If you miss a submission deadline or an exam, your marks will be rescaled (based on other assignments) ONLY in exceptional circumstances (medical reason for example). These must be approved by me BEFORE the due date in writing or via email. The default for not turning in homework is that you get zero.
  • Texts/References
    1. Introductory Techniques for 3D Computer Vision, Trucco and Verri. Prentice Hall.
    2. Other References in no particular order
      • Gonzalez, R. C. and Woods, R. E. [2002]. Digital Image Processing, 2nd ed., Prentice Hall, Upper Saddle River, NJ.
      • Digital Image Processing by A. K. Jain (hard to read).
      • Digital Image Processing by Pratt.
      • Hanselman, D. and Littlefield, B. [2001]. Mastering MATLAB 6, Prentice Hall, Upper Saddle River, NJ.
  • Old Announcements
    1. Grades so far has been updated. If you have questions, please MEET me on Tuesday or Thursday after class. This is your last chance to make sure that the scores posted are neither too much nor too little (based on the sheets you have received).
    2. Looks like most people have taken part in the course evaluation, I would like to close the evaluation soon.
    3. Please participate in the course evaluation.
    4. Exam returned on 2/20 (Thursday): 5:00 PM
    5. Exam on 2/19 (Wednesday): 9:30 AM.
    6. Programming assignment due on 2/12
    7. Task number 1 due on 2/6.
    8. Honor Code: 
        I pledge on my honour that I have not given or received any
  unauthorized assistance 
  on this assignment or any previous homework.
      If you are not clear what unauthorized assistance means, please talk to me.
    9. Please make sure that you are signed up on the mailing list. You can subscribe to the mailing list by visiting http://bhim/mailman/listinfo/cs622. Enter your email address and pick a password. You will get a confirmation email. Reply to it to confirm your subscription.
    10. People in the course. (Officially registered students will have marks against their names in the grades list.
  • Solutions I used to post solutions, but nowadays I hand them out in class. Solutions may be occasionally posted and deleted asynchronously (in order that students from other courses do not suffer/benefit). 
  • Mid term Course Evaluation.
    1. The questions.
    2. Thank you for your feedback. The evaluation process has been completed (9 people responded. let me know if you still want to say something though). Here are the results
      1. Overall what the students thought.
      2. The course organization.
      3. Individual Responses what the students thought. Look for yours here! Also comments appear only on this page.
      4. The average response. Look for towers on the right.
      5. The bane for students: Evaluation and faculty alike!
      6. And how were the lectures handled by the professor?